CS 328 Introduction to Data Science

World Inequality Analysis

Aditya Shukla, 22120032, aditya.shukla@iitgn.ac.in

Tejas Parmar, 20110125, parmar.tejas@iitgn.ac.in

Deep Thakkar, 19110009, deep.st@iitgn.ac.in

Simran Saini, 20110200, simran.saini@iitgn.ac.in

Analysis of Life Expectancy based on World Inequality Parameters

Explaining the Data Set

The life expectancy dataset is a collection of data from various countries around the globe, which providies information on factors that can influence life expectancy. This dataset consists of 22 variables, some of them being: the country, year, life expectancy, GDP, population, schooling, etc.

The data spans over the years from 2000 to 2015. The souces for this data include: the World Health Organization (WHO), the United Nations (UN), the World Bank (WB). This dataset contains data from 193 countries around the world, making it a comprehensive source of information on global health trends.

The dataset is available in CSV format and accessible for analysis. It is used to study the impact of socioeconomic factors on health outcomes, such as life expectancy. It enabled us to study the relationship between various factors, such as income, education, and health. The dataset also provides insights into the disparities in health outcomes between countries and regions. The dataset has been pre-processed and cleaned to ensure that the data is consistent and accurate.

The world income inequality dataset has multiple tables containing different observations of each countries over the span of around 50 years. dataset "income-share-of-the-top-10-pip" consists of Country, Code, Year, Share of the richest decile in total income or expenditure. dataset "income-shares-by-quintile" consists of Country, Code, Year, Share of each quintile in the total income or expenditure. The dataset has been collected from a source cited in the citations section. The dataset is easily accessible for analysis. It is used for studying the inequalities in countries over the years by comparing their richest and poorest quintiles. The dataset has been already pre-processed and cleaned to ensure that data is consistent and accurate.

Objective

The main objective of our project is to understand and visulaize the disparity in life expectancy among countries.

For these we have considered various parameters like development status ( developed or developing), Schooling , GDP etc.**

In this Project we analyze the life expectancy data of different countries and explore various factors that affect the life expectancy of countries. We have utlized various data analysis techniques such as hypothesis testing, time series forecasting, and clustering to gain insights and make informed decisions based on the data.

Through this project we also aim to create interactive visualizations to better communicate the findings and provide a better understanding of the data.

Data Exploration

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.graph_objs as go
import plotly.tools as tls
import plotly.offline as py
import warnings
warnings.filterwarnings('ignore')

df = pd.read_csv('Life Expectancy Data.csv')

df

	Country	Year	Status	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	...	Polio	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling
0	Afghanistan	2015	Developing	65.0	263.0	62	0.01	71.279624	65.0	1154	...	6.0	8.16	65.0	0.1	584.259210	33736494.0	17.2	17.3	0.479	10.1
1	Afghanistan	2014	Developing	59.9	271.0	64	0.01	73.523582	62.0	492	...	58.0	8.18	62.0	0.1	612.696514	327582.0	17.5	17.5	0.476	10.0
2	Afghanistan	2013	Developing	59.9	268.0	66	0.01	73.219243	64.0	430	...	62.0	8.13	64.0	0.1	631.744976	31731688.0	17.7	17.7	0.470	9.9
3	Afghanistan	2012	Developing	59.5	272.0	69	0.01	78.184215	67.0	2787	...	67.0	8.52	67.0	0.1	669.959000	3696958.0	17.9	18.0	0.463	9.8
4	Afghanistan	2011	Developing	59.2	275.0	71	0.01	7.097109	68.0	3013	...	68.0	7.87	68.0	0.1	63.537231	2978599.0	18.2	18.2	0.454	9.5
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2933	Zimbabwe	2004	Developing	44.3	723.0	27	4.36	0.000000	68.0	31	...	67.0	7.13	65.0	33.6	454.366654	12777511.0	9.4	9.4	0.407	9.2
2934	Zimbabwe	2003	Developing	44.5	715.0	26	4.06	0.000000	7.0	998	...	7.0	6.52	68.0	36.7	453.351155	12633897.0	9.8	9.9	0.418	9.5
2935	Zimbabwe	2002	Developing	44.8	73.0	25	4.43	0.000000	73.0	304	...	73.0	6.53	71.0	39.8	57.348340	125525.0	1.2	1.3	0.427	10.0
2936	Zimbabwe	2001	Developing	45.3	686.0	25	1.72	0.000000	76.0	529	...	76.0	6.16	75.0	42.1	548.587312	12366165.0	1.6	1.7	0.427	9.8
2937	Zimbabwe	2000	Developing	46.0	665.0	24	1.68	0.000000	79.0	1483	...	78.0	7.10	78.0	43.5	547.358878	12222251.0	11.0	11.2	0.434	9.8

2938 rows × 22 columns

df.head()
df.info()
df.describe()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2938 entries, 0 to 2937
Data columns (total 22 columns):
 #   Column                           Non-Null Count  Dtype  
---  ------                           --------------  -----  
 0   Country                          2938 non-null   object 
 1   Year                             2938 non-null   int64  
 2   Status                           2938 non-null   object 
 3   Life expectancy                  2928 non-null   float64
 4   Adult Mortality                  2928 non-null   float64
 5   infant deaths                    2938 non-null   int64  
 6   Alcohol                          2744 non-null   float64
 7   percentage expenditure           2938 non-null   float64
 8   Hepatitis B                      2385 non-null   float64
 9   Measles                          2938 non-null   int64  
 10   BMI                             2904 non-null   float64
 11  under-five deaths                2938 non-null   int64  
 12  Polio                            2919 non-null   float64
 13  Total expenditure                2712 non-null   float64
 14  Diphtheria                       2919 non-null   float64
 15   HIV/AIDS                        2938 non-null   float64
 16  GDP                              2490 non-null   float64
 17  Population                       2286 non-null   float64
 18   thinness  1-19 years            2904 non-null   float64
 19   thinness 5-9 years              2904 non-null   float64
 20  Income composition of resources  2771 non-null   float64
 21  Schooling                        2775 non-null   float64
dtypes: float64(16), int64(4), object(2)
memory usage: 505.1+ KB

	Year	Life expectancy	Adult Mortality	infant deaths	Alcohol	percentage expenditure	Hepatitis B	Measles	BMI	under-five deaths	Polio	Total expenditure	Diphtheria	HIV/AIDS	GDP	Population	thinness 1-19 years	thinness 5-9 years	Income composition of resources	Schooling
count	2938.000000	2928.000000	2928.000000	2938.000000	2744.000000	2938.000000	2385.000000	2938.000000	2904.000000	2938.000000	2919.000000	2712.00000	2919.000000	2938.000000	2490.000000	2.286000e+03	2904.000000	2904.000000	2771.000000	2775.000000
mean	2007.518720	69.224932	164.796448	30.303948	4.602861	738.251295	80.940461	2419.592240	38.321247	42.035739	82.550188	5.93819	82.324084	1.742103	7483.158469	1.275338e+07	4.839704	4.870317	0.627551	11.992793
std	4.613841	9.523867	124.292079	117.926501	4.052413	1987.914858	25.070016	11467.272489	20.044034	160.445548	23.428046	2.49832	23.716912	5.077785	14270.169342	6.101210e+07	4.420195	4.508882	0.210904	3.358920
min	2000.000000	36.300000	1.000000	0.000000	0.010000	0.000000	1.000000	0.000000	1.000000	0.000000	3.000000	0.37000	2.000000	0.100000	1.681350	3.400000e+01	0.100000	0.100000	0.000000	0.000000
25%	2004.000000	63.100000	74.000000	0.000000	0.877500	4.685343	77.000000	0.000000	19.300000	0.000000	78.000000	4.26000	78.000000	0.100000	463.935626	1.957932e+05	1.600000	1.500000	0.493000	10.100000
50%	2008.000000	72.100000	144.000000	3.000000	3.755000	64.912906	92.000000	17.000000	43.500000	4.000000	93.000000	5.75500	93.000000	0.100000	1766.947595	1.386542e+06	3.300000	3.300000	0.677000	12.300000
75%	2012.000000	75.700000	228.000000	22.000000	7.702500	441.534144	97.000000	360.250000	56.200000	28.000000	97.000000	7.49250	97.000000	0.800000	5910.806335	7.420359e+06	7.200000	7.200000	0.779000	14.300000
max	2015.000000	89.000000	723.000000	1800.000000	17.870000	19479.911610	99.000000	212183.000000	87.300000	2500.000000	99.000000	17.60000	99.000000	50.600000	119172.741800	1.293859e+09	27.700000	28.600000	0.948000	20.700000

df = df.fillna(df.mean())

Correlation Matrix and Heatmap

corr_matrix = df.corr()
sns.heatmap(corr_matrix)
plt.show()

From this Coorelation Matric we are able to interpret that Life expectacy has a high coorelationship between 'Life Expectance and Income composition' and 'Life Expectancy and Schooling' very high.

It has a moderate correlationship with 'Alcoholism', 'Percentage expenditure', 'BMI', 'select diseases', and 'GDP'. Whereas it has a very weak coorelationship with factors like 'thinness', 'infant mortality', etc.

Distribution of life expectancy by Development Status of Country

We have obtained a box plot of life expectancy vs development status of a country.

import seaborn as sns

sns.boxplot(x='Status', y='Life expectancy ', data=df)
plt.xlabel('Status')
plt.ylabel('Life expectancy')
plt.title('Distribution of life expectancy by status')
plt.show()

From the above box plot we can conclude that the developed countries have a higher median life expectancy than developing countries, with less variability in the distribution. The box plot also shows that developing countries have a wider range of life expectancies, with some countries having very low life expectancy. This can be due to various levels of development a country is in.

Countries with least Life Expectancy over the years

import plotly.graph_objs as go
def get_top6_countries(df, year):
    df_year = df[df['Year'] == year]
    return df_year.nsmallest(6, 'Life expectancy ')

years = df['Year'].unique().tolist()


fig = go.Figure()

df_initial = get_top6_countries(df, years[0])
fig.add_trace(go.Bar(x=df_initial['Country'], y=df_initial['Life expectancy '], name=str(years[0])))

fig.update_layout(title='Countries with the least Life Expectancy', xaxis_title='Country', yaxis_title='Life Expectancy (years)',
                  xaxis={'type': 'category'}, yaxis_range=[0, 100], barmode='group')

slider = dict(
    active=0,
    pad={"t": 50},
    steps=[],
)


for year in years:
    df_top6 = get_top6_countries(df, year)
    countries = df_top6['Country'].tolist()
    slider['steps'].append(dict(label=str(year), method="update", args=[{"x": [countries], "y": [df_top6['Life expectancy '].tolist()], "visible": [True]},
                                                                          {"title": str(year)}]))
    

fig.update_layout(sliders=[slider])

# Display the figure
fig.show()

From the above plot we can interpret that through the years the lowest life for counties is increasing, thic can be atributed to development in medical scince and increase in sharing of medical resouces by bteer off countries.

Another importnat observation is that most of the countries over this 15 years data period belong to the underdeveloped regions of Africa.

Countries with highest life expectancies over the years

import plotly.graph_objs as go
def get_top6_countries(df, year):
    df_year = df[df['Year'] == year]
    return df_year.nlargest(6, 'Life expectancy ')

years = df['Year'].unique().tolist()


fig = go.Figure()

df_initial = get_top6_countries(df, years[0])
fig.add_trace(go.Bar(x=df_initial['Country'], y=df_initial['Life expectancy '], name=str(years[0])))

fig.update_layout(title='Countries with the  Highest Life Expectancy', xaxis_title='Country', yaxis_title='Life Expectancy (years)',
                  xaxis={'type': 'category'}, yaxis_range=[0, 100], barmode='group')

slider = dict(
    active=0,
    pad={"t": 50},
    steps=[],
)


for year in years:
    df_top6 = get_top6_countries(df, year)
    countries = df_top6['Country'].tolist()
    slider['steps'].append(dict(label=str(year), method="update", args=[{"x": [countries], "y": [df_top6['Life expectancy '].tolist()], "visible": [True]},
                                                                          {"title": str(year)}]))
    

fig.update_layout(sliders=[slider])

# Display the figure
fig.show()

From the above plot we can interpret that the life highest expectancy is increasing over the years. This can be atributed to developments in medicine and the ease of avaibility to those to these counties.

Another important observation from this plot is that most of the counties in this plot are developed counties in Europe or North America.

Life Expectancy and Alcohol

import plotly.express as px


df_alcohol = df[['Country', 'Year', 'Life expectancy ', 'Alcohol']]


fig = px.scatter(df_alcohol, x='Alcohol', y='Life expectancy ', color='Country', animation_frame='Year',
                 range_x=[0, 20], range_y=[20, 90], height=500)


fig.update_layout(title='Life Expectancy vs. Alcohol Consumption by Country',
                  xaxis_title='Alcohol Consumption (liters per capita)',
                  yaxis_title='Life Expectancy (years)')

fig.show()

From this plot we can conclude that alcolohol consumption per capitia has overall decreased but it has no corelation with teh life expectancy. This helps prove that the genral social belief in conservatiove contries taht alcohol consumption is bad for health and can reduce life is not stronly true.

Life Expectancy and Income composition of resources

import scipy as sp

sns.scatterplot(x='Income composition of resources', y='Life expectancy ', data=df)
plt.show()

The above plot shows the relationship between life expectancy and income composition of resources is very high. The almost linear trend with a positive slope hints that there is a strong positive correlation between the two variables. Thus, indicating that countries with higher income composition of resources tend to have higher life expectancies and vice versa.

import plotly.express as px

fig = px.choropleth(df, locations='Country', locationmode='country names', color='Life expectancy ', 
                    hover_name='Country', animation_frame='Year', range_color=[20, 90])
fig.update_layout(title_text='World Life Expectancy over the Years (2000-2015)')
fig.show()

From the abobe plot also we can interpret that the lowest life expectancy is generally observed in the underdeveoped regions of Africa whereas the highest in observed in the developed regions of Europe, North America and Eastern Asia.

df_india = df[df['Country'] == 'India']

# Create interactive line graph
fig = px.line(df_india, x='Year', y='Life expectancy ',
              title='Life Expectancy in India (Year-wise)',
              hover_data={'Life expectancy ': ':.1f'})
fig.update_layout(xaxis_title='Year', yaxis_title='Life Expectancy')
fig.update_traces(mode='markers+lines', marker=dict(size=8, line=dict(width=2)))
fig.show()

From the above plot we are able to interpet that the life expectnacy in our nation India,m is steadily increasing with a positive slope which can be atributed to the medical advances.

import plotly.graph_objs as go

countries = ['India', 'China', 'United States of America', 'France', 'Japan', 'United Kingdom of Great Britain and Northern Ireland']

traces = []

for country in countries:
    df_country = df[df['Country'] == country]
    trace = go.Scatter(x=df_country['Year'], y=df_country['Life expectancy '], name=country, marker=dict(size=8))
    traces.append(trace)

layout = go.Layout(
    title='Life Expectancy of Selected Countries',
    xaxis=dict(
        title='Year',
        ticklen=5,
        zeroline=False,
        gridwidth=2,
    ),
    yaxis=dict(
        title='Life Expectancy',
        ticklen=5,
        gridwidth=2,
    ),
    showlegend=True,
    hovermode='closest',
)

fig = go.Figure(data=traces, layout=layout)
fig.show()

From the above plot we observe and unexplained increase in the life expectancy of France and United Kingdom

Hypothesis Testing

Hypothesis 1:

Null hypothesis: There is no significant difference in life expectancy between developed and developing countries.

Alternative hypothesis: There is a significant difference in life expectancy between developed and developing countries.

from scipy.stats import ttest_ind

developed = df[df['Status'] == 'Developed']['Life expectancy ']
developing = df[df['Status'] == 'Developing']['Life expectancy ']

t_stat, p_val = ttest_ind(developed, developing)

print('t-statistic:', t_stat)
print('p-value:', p_val)

t-statistic: 29.805188781530223
p-value: 9.034938663789684e-171

# Significance level
alpha = 0.05

if p_val < alpha:
    print("Reject null hypothesis")
else:
    print("Fail to reject null hypothesis")

Reject null hypothesis

Interpretation: We have conducted a two-sample t-test to compare the life expectancy of developed and developing countries. The t-statistic obtained from the test was 29.805, and the p-value was 9.034e-171. We set the significance level (alpha) at 0.05. Since the p-value (9.034e-171) is less than the significance level (0.05), we reject the null hypothesis.

Finding correleation between columns and Displaying those factors contributing most to the life expectancy in developed and developing countries

cols = ['Year', 'Status', 'Life expectancy ', 'Adult Mortality', 'Alcohol','Hepatitis B', 'Polio', 'Total expenditure', 'Diphtheria ', 'GDP', 'Population', 'Income composition of resources', 'Schooling']
df1 = df[cols]


df1['Status'] = df1['Status'].apply(lambda x: 1 if x == 'Developed' else 0)


df1.dropna(inplace=True)


corr = df1.corr()

sns.heatmap(corr, cmap='coolwarm')
plt.title('Correlation Matrix of Life Expectancy Factors')
plt.show()

from the above plt we observe that teh development status of a country has a strong corelationship with alcohol consumption but as we observed above alcohol consumption does not have a strong coorelationship with Life expectancy.

developed = df[df['Status'] == 'Developed']
developing = df[df['Status'] == 'Developing']

corr_matrix_developed = developed.corr()


corr_matrix_developing = developing.corr()

corr_developed = corr_matrix_developed['Life expectancy '].sort_values(ascending=False)


corr_developing = corr_matrix_developing['Life expectancy '].sort_values(ascending=False)

print("Top three correlations for developed countries:")
print(corr_developed[1:4])
print("\nTop three correlations for developing countries:")
print(corr_developing[1:4])

Top three correlations for developed countries:
Income composition of resources    0.473753
GDP                                0.363391
Schooling                          0.351472
Name: Life expectancy , dtype: float64

Top three correlations for developing countries:
Schooling                          0.647412
Income composition of resources    0.610979
 BMI                               0.545419
Name: Life expectancy , dtype: float64

Life Expectancy by Country Development Status (Year-wise)

df_grouped = df.groupby(['Year', 'Status'], as_index=False).mean()


fig = go.Figure()


developed_data = df_grouped[df_grouped['Status'] == 'Developed']
fig.add_trace(go.Scatter(x=developed_data['Year'], y=developed_data['Life expectancy '], mode='lines+markers',
                         name='Developed', marker=dict(size=8, line=dict(width=2)), 
                         hovertemplate='Year: %{x}<br>Life Expectancy: %{y:.1f}<extra></extra>'))


developing_data = df_grouped[df_grouped['Status'] == 'Developing']
fig.add_trace(go.Scatter(x=developing_data['Year'], y=developing_data['Life expectancy '], mode='lines+markers',
                          name='Developing', marker=dict(size=8, line=dict(width=2)), 
                          hovertemplate='Year: %{x}<br>Life Expectancy: %{y:.1f}<extra></extra>'))


fig.update_layout(title_text='Life Expectancy by Country Development Status (Year-wise)',
                  xaxis_title='Year', yaxis_title='Life Expectancy', hovermode='x',
                  legend=dict(x=0, y=1, bgcolor='rgba(255, 255, 255, 0.5)', bordercolor='rgba(0, 0, 0, 0)'),
                  annotations=[go.layout.Annotation(x=year, y=90, xref='x', yref='y', text=str(year), showarrow=True,
                                                     arrowhead=2, arrowsize=1, arrowwidth=1,
                                                     ax=-20, ay=-30, bordercolor='black', borderwidth=2,
                                                     bgcolor='white') for year in range(2000, 2016)])

fig.show()

The above graph shows the trend in life expectancy over the years for developed and developing countries. The blue line represents developed countries, while the orange line represents developing countries.

From the graph, it is clear that the life expectancy in developed countries has been consistently higher than that in developing countries over the years. The trend shows a gradual increase in life expectancy for both developed and developing countries, but the gap between them remains significant. The differece between the developed and developing countries is decreasing but decreasing very slowly.

Cluster Analysis of Life Expectancy Data

from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
df_cluster = df[['Country', 'Year', 'Life expectancy ', 'GDP', 'Population', 'Schooling','Income composition of resources']]


scaler = StandardScaler()
df_scaled = scaler.fit_transform(df_cluster.iloc[:, 2:])

kmeans = KMeans(n_clusters=2, random_state=42).fit(df_scaled)


df_cluster['Cluster'] = kmeans.labels_


fig = px.scatter_3d(df_cluster, x='Income composition of resources', y='Schooling', z='Life expectancy ', color='Cluster',
                    hover_name='Country', animation_frame='Year', range_color=[0, 2])
fig.update_layout(title_text='Cluster Analysis of Life Expectancy Data')
fig.show()

Interpretations:

We chose to perform cluster analysis of Income compostion and schooling as they had strong corelationship with life expectancy.

Based on the scatter plot, it can be observed that there are two distinct clusters of countries based on their life expectancy, income composition of resources, and schooling,GDP. The blue cluster represents countries with high life expectancy, while the purple cluster represents countries with low life expectancy.

It is also worth noting that the countries in the blue cluster generally have a higher income composition of resources and schooling compared to countries in the purple cluster. This suggests that these factors may play a role in determining life expectancy.

Overall, the cluster analysis provides further evidence to support the claim that there is a significant difference in life expectancy between developed and developing countries, as indicated by the distinct clusters of countries with high and low life expectancy.

Economic inequality for each country over the years.

Indented block

import plotly.express as px
import pandas as pd
import numpy as np
import plotly.graph_objects as go

# Load data
Eco_df = pd.read_csv('income-shares-by-quintile-pip.csv')

# List of countries
countries = Eco_df['Country'].unique()

Eco_df

	Country	Code	Year	Share of the richest quintile in total income or expenditure	Share of the 4th quintile in total income or expenditure	Share of the 3rd quintile in total income or expenditure	Share of the 2nd quintile in total income or expenditure	Share of the poorest quintile in total income or expenditure
0	Albania	ALB	1996	36.115121	23.296956	17.734564	13.700725	9.152633
1	Albania	ALB	2002	40.360715	22.213014	16.492562	12.580263	8.353446
2	Albania	ALB	2005	39.175111	22.498552	17.025227	12.898465	8.402645
3	Albania	ALB	2008	38.993515	22.227811	16.836211	13.072056	8.870407
4	Albania	ALB	2012	37.823477	22.808756	17.340775	13.174370	8.852622
...	...	...	...	...	...	...	...	...
2117	Zambia	ZMB	2006	59.468406	19.145137	11.054804	6.786949	3.544705
2118	Zambia	ZMB	2010	61.050270	17.889969	10.488170	6.761818	3.809772
2119	Zambia	ZMB	2015	61.267680	19.278932	10.569799	5.999579	2.884011
2120	Zimbabwe	ZWE	2011	49.664463	21.011286	14.002204	9.497565	5.824482
2121	Zimbabwe	ZWE	2017	51.111684	20.631633	13.171137	9.121204	5.964342

2122 rows × 8 columns

# X axis is the Year from 1977 to 2019 and Y axis is the % of income or expenditure.
# The figure contains 5 areas for each quintile seperated by lines with different colors.
# The color of the area is the same as the color of the line.
fig = px.area(Eco_df[Eco_df['Country'] == 'India'], x="Year", y=["Share of the richest quintile in total income or expenditure", "Share of the 4th quintile in total income or expenditure", "Share of the 3rd quintile in total income or expenditure", "Share of the 2nd quintile in total income or expenditure", "Share of the poorest quintile in total income or expenditure"], color_discrete_sequence=['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd'])
fig.update_layout(
    title="Share of income or expenditure by quintile over time in selected country",
    xaxis_title="Year",
    yaxis_title="Share of income or expenditure (%)",
    legend_title="Quintile",
    font=dict(
        family="Courier New, monospace",
        size=18,
        color="RebeccaPurple"
    )
)



fig.update_layout(
    updatemenus=[
        dict(
            buttons=list([
                dict(
                    args=[{"y": [Eco_df[Eco_df['Country'] == country]['Share of the richest quintile in total income or expenditure'], Eco_df[Eco_df['Country'] == country]['Share of the 4th quintile in total income or expenditure'], Eco_df[Eco_df['Country'] == country]['Share of the 3rd quintile in total income or expenditure'], Eco_df[Eco_df['Country'] == country]['Share of the 2nd quintile in total income or expenditure'], Eco_df[Eco_df['Country'] == country]['Share of the poorest quintile in total income or expenditure']]}],
                    label=country,
                    method="update"
                ) for country in countries
            ]),
            direction="down",
            pad={"r": 10, "t": 10},
            showactive=True,
            x=0.1,
            xanchor="left",
            y=1.1,
            yanchor="top"
        ),
    ],
)


fig.update_layout(
    xaxis=dict(
        rangeslider=dict(
            visible=True
        ),
        type="date"
    )
)


fig.show()

Interpretations: Here you can see the portion/area acquired by all five quintiles where richest quintile is acquiring almost 30-40% wealth/income of the country's expenditure. Overall you can scroll the timeline bar to observe the curve in a more accurate manner. You can select the country from the menu button and the graph will change accordingly.

Share of the income is steadily increased by a small growth rate for many countries which reflects to the overall increasing world inequality.

Forecasting Future Life Expectancy of Developed and Developing Countries

import plotly.graph_objs as go
import plotly.offline as pyo
from statsmodels.tsa.arima.model import ARIMA
warnings.filterwarnings('ignore')

df1 = df.copy()
df1['Year'] = pd.to_datetime(df1['Year'], format='%Y')

df_dev = df1[df1['Status'] == 'Developed']
df_dev_avg = df_dev.groupby('Year')['Life expectancy '].mean().reset_index()

df_devp = df1[df1['Status'] == 'Developing']
df_devp_avg = df_devp.groupby('Year')['Life expectancy '].mean().reset_index()

model_devp = ARIMA(df_devp_avg['Life expectancy '], order=(1,1,1))
model_devp_fit = model_devp.fit()
forecast_devp = model_devp_fit.forecast(steps=10)


model_dev = ARIMA(df_dev_avg['Life expectancy '], order=(1,1,1))
model_dev_fit = model_dev.fit()
forecast_dev = model_dev_fit.forecast(steps=10)

fig = go.Figure()

fig.add_trace(go.Scatter(x=df_dev_avg['Year'], y=df_dev_avg['Life expectancy '],
                    mode='lines+markers', name='Developed Historical Data'))

fig.add_trace(go.Scatter(x=df_devp_avg['Year'], y=df_devp_avg['Life expectancy '],
                    mode='lines+markers', name='Developing Historical Data'))

fig.add_trace(go.Scatter(x=pd.date_range(start='2016', periods=10, freq='Y'), y=forecast_dev,
                    mode='lines+markers', name='Developed Forecast'))

fig.add_trace(go.Scatter(x=pd.date_range(start='2016', periods=10, freq='Y'), y=forecast_devp,
                    mode='lines+markers', name='Developing Forecast'))

fig.update_layout(title='Life Expectancy Forecast for Developed and Developing Countries',
                   xaxis_title='Year',
                   yaxis_title='Life Expectancy')

fig.update_traces(hoverinfo='text', hovertext=[f'Year: {year}<br>Life Expectancy: {life_expectancy:.2f}'
                                               for year, life_expectancy in zip(df_dev_avg['Year'], df_dev_avg['Life expectancy '])],
                  selector=dict(mode='lines+markers', name='Developed Historical Data'))

fig.update_traces(hoverinfo='text', hovertext=[f'Year: {year}<br>Life Expectancy: {life_expectancy:.2f}'
                                               for year, life_expectancy in zip(df_devp_avg['Year'], df_devp_avg['Life expectancy '])],
                  selector=dict(mode='lines+markers', name='Developing Historical Data'))

fig.update_traces(hoverinfo='text', hovertext=[f'Year: {year}<br>Life Expectancy Forecast: {life_expectancy:.2f}'
                                               for year, life_expectancy in zip(pd.date_range(start='2016', periods=10, freq='Y'), forecast_dev)],
                  selector=dict(mode='lines+markers', name='Developed Forecast'))

fig.update_traces(hoverinfo='text', hovertext=[f'Year: {year}<br>Life Expectancy Forecast: {life_expectancy:.2f}'
                                               for year, life_expectancy in zip(pd.date_range(start='2016', periods=10, freq='Y'), forecast_devp)],
                  selector=dict(mode='lines+markers', name='Developing Forecast'))

pyo.iplot(fig)

Interpretation: Based on the time series forecasting graph, we can see that the life expectancy of developing countries is predicted to continue increasing steadily over the next 10 years. This supports our claim that there is a significant difference in life expectancy between developed and developing countries. Additionally, the forecasted line for developed countries has smaller slope, indicating that the life expectancy in these countries is already quite high and due to biological constraints is not expected to increase significantly in the future that is they have reached a saturation level. On the contraray the forcasted line of devloping countries has a higher slope and thus teh gap in life expectancy between developed and developing countries is stedilay decreasing.

Hypothesis 2:
Null Hypothesis: There is no significant relationship between life expectancy and GDP, schooling, and income composition.

Alternative Hypothesis: There is a significant relationship between life expectancy and GDP, schooling, and income composition.

In this hypothesis testing we will be using OLS Regression.

Ordinary Least Squares (OLS) regression is a widely used statistical method for estimating the relationship between a dependent variable and one or more independent variables. The main principle of OLS is to minimize the sum of the squared differences between the observed dependent variable values and the predicted values obtained from the regression model.

import statsmodels.api as sm
X = df[["GDP", "Schooling", "Income composition of resources"]]
y = df["Life expectancy "]

X = sm.add_constant(X)


model = sm.OLS(y, X).fit()

print(model.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:       Life expectancy    R-squared:                       0.563
Model:                            OLS   Adj. R-squared:                  0.563
Method:                 Least Squares   F-statistic:                     1260.
Date:                Mon, 01 May 2023   Prob (F-statistic):               0.00
Time:                        00:34:14   Log-Likelihood:                -9568.7
No. Observations:                2938   AIC:                         1.915e+04
Df Residuals:                    2934   BIC:                         1.917e+04
Df Model:                           3                                         
Covariance Type:            nonrobust                                         
===================================================================================================
                                      coef    std err          t      P>|t|      [0.025      0.975]
---------------------------------------------------------------------------------------------------
const                              44.9416      0.463     97.036      0.000      44.033      45.850
GDP                              8.281e-05   9.94e-06      8.329      0.000    6.33e-05       0.000
Schooling                           1.2307      0.059     20.728      0.000       1.114       1.347
Income composition of resources    14.1886      0.952     14.907      0.000      12.322      16.055
==============================================================================
Omnibus:                      255.801   Durbin-Watson:                   0.295
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              835.132
Skew:                          -0.422   Prob(JB):                    4.50e-182
Kurtosis:                       5.471   Cond. No.                     1.24e+05
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.24e+05. This might indicate that there are
strong multicollinearity or other numerical problems.

Interpretation: In the given OLS regression results:

Dependent variable: Life expectancy is the dependent variable, as we want to analyze the effect of GDP, schooling, and income composition of resources (independent variables) on life expectancy.

Model: The OLS model provides the best approximation of the true population regression line by minimizing the squared errors between the observed and predicted values

Coefficients and p-values:

GDP: The coefficient for GDP is 8.281e-05, with a p-value less than 0.05, indicating a significant positive relationship between GDP and life expectancy. As GDP increases, life expectancy is expected to increase by 8.281e-05 units, holding other factors constant.

Schooling: The coefficient for schooling is 1.2307, with a p-value less than 0.05, indicating a significant positive relationship between schooling and life expectancy. As schooling increases, life expectancy is expected to increase by 1.2307 units, holding other factors constant.

Income composition of resources: The coefficient for income composition of resources is 14.1886, with a p-value less than 0.05, indicating a significant positive relationship between income composition of resources and life expectancy. As the income composition of resources increases, life expectancy is expected to increase by 14.1886 units, holding other factors constant.

In conclusion, the OLS regression results show that there is a significant relationship between life expectancy and GDP, schooling, and income composition of resources. The coefficients for these independent variables indicate the direction and magnitude of their impact on life expectancy.

# Scatter plot for life expectancy vs. schooling
fig_schooling = px.scatter(df, x="Schooling", y="Life expectancy ", color="Status", 
                           hover_name="Country", animation_frame="Year")
fig_schooling.update_layout(title="Life Expectancy vs. Schooling")
fig_schooling.show()

# Scatter plot for life expectancy vs. income composition of resources
fig_income = px.scatter(df, x="Income composition of resources", y="Life expectancy ", color="Status", 
                        hover_name="Country", animation_frame="Year")
fig_income.update_layout(title="Life Expectancy vs. Income Composition of Resources")
fig_income.show()

Interpretation: We can observed the trends and relationships between life expectancy and the variables (schooling and income composition of resources). These visualizations support the findings from the OLS regression analysis, indicating a positive relationship between life expectancy and the independent variables.

Conclusion

In this project we have successfully analysed and done hypothesis testing on disparity and dependency of life expectency on various parameters among countries. We have also given the required interpretations for our finding through hypothesis testing to support our claim.

Our Findings

(1) We have found out that there is significant difference in the life expectency between developed and developed countries.

(2) Life Expectency depends on Schooling and Income composition of resources.

(3) Life Expectnacy of the developed countries is expected to increase at a slower rate as compared to the life expectancy in the developing countries. The gap between the two dicision is steadily decreasing.

(4) Life expectancy when view as a global distribution, interprets as higher liufe expectancy in Europe, North America, and Eastern Asia. Where there is lower Life Expectancy in Africa

Citations:

Life Expectancy Kaggle Dataset

Max Roser (2013) - "Global Economic Inequality". Published online at OurWorldInData.org. Retrieved from: https://ourworldindata.org/global-economic-inequality